lukecq commited on
Commit
c5c3152
·
verified ·
1 Parent(s): 04fa9ff

add paper link and SeaBench-Audio

Browse files
Files changed (1) hide show
  1. README.md +10 -7
README.md CHANGED
@@ -24,13 +24,16 @@ tags:
24
  <p align="center">
25
  <a href="https://DAMO-NLP-SG.github.io/SeaLLMs-Audio/" target="_blank" rel="noopener">Website</a>
26
  &nbsp;&nbsp;
 
 
27
  <a href="https://huggingface.co/spaces/SeaLLMs/SeaLLMs-Audio-Demo" target="_blank" rel="noopener"> 🤗 DEMO</a>
28
  &nbsp;&nbsp;
29
  <a href="https://github.com/DAMO-NLP-SG/SeaLLMs-Audio" target="_blank" rel="noopener">Github</a>
30
  &nbsp;&nbsp;
31
  <a href="https://huggingface.co/SeaLLMs/SeaLLMs-Audio-7B" target="_blank" rel="noopener">🤗 Model</a>
32
  &nbsp;&nbsp;
33
- <!-- <a href="https://arxiv.org/pdf/2407.19672" target="_blank" rel="noopener">[NEW] Technical Report</a> -->
 
34
  </p>
35
 
36
  We introduce **SeaLLMs-Audio**, the multimodal (audio) extension of the [SeaLLMs](https://damo-nlp-sg.github.io/DAMO-SeaLLMs/) (Large Language Models for Southeast Asian languages) family. It is the first large audio-language model (LALM) designed to support multiple Southeast Asian languages, including **Indonesian (id), Thai (th), and Vietnamese (vi), alongside English (en) and Chinese (zh)**.
@@ -230,12 +233,12 @@ If you find our project useful, we hope you would kindly star our [repo](https:/
230
  Corresponding Author: Wenxuan Zhang ([[email protected]](mailto:[email protected]))
231
  ```
232
  @misc{SeaLLMs-Audio,
233
- author = {Chaoqun Liu and Mahani Aljunied and Guizhen Chen and Hou Pong Chan and Weiwen Xu and Yu Rong and Wenxuan Zhang},
234
- title = {SeaLLMs-Audio: Large Audio-Language Models for Southeast Asia},
235
- year = {2025},
236
- publisher = {GitHub},
237
- journal = {GitHub repository},
238
- howpublished = {\url{https://github.com/DAMO-NLP-SG/SeaLLMs-Audio}},
239
  }
240
  ```
241
 
 
24
  <p align="center">
25
  <a href="https://DAMO-NLP-SG.github.io/SeaLLMs-Audio/" target="_blank" rel="noopener">Website</a>
26
  &nbsp;&nbsp;
27
+ <a href="https://arxiv.org/abs/2511.01670" target="_blank" rel="noopener">📖 Paper</a>
28
+ &nbsp;&nbsp;
29
  <a href="https://huggingface.co/spaces/SeaLLMs/SeaLLMs-Audio-Demo" target="_blank" rel="noopener"> 🤗 DEMO</a>
30
  &nbsp;&nbsp;
31
  <a href="https://github.com/DAMO-NLP-SG/SeaLLMs-Audio" target="_blank" rel="noopener">Github</a>
32
  &nbsp;&nbsp;
33
  <a href="https://huggingface.co/SeaLLMs/SeaLLMs-Audio-7B" target="_blank" rel="noopener">🤗 Model</a>
34
  &nbsp;&nbsp;
35
+ <a href="https://huggingface.co/datasets/SeaLLMs/SeaBench-Audio" target="_blank" rel="noopener">🤗 Benchmark</a>
36
+ &nbsp;&nbsp;
37
  </p>
38
 
39
  We introduce **SeaLLMs-Audio**, the multimodal (audio) extension of the [SeaLLMs](https://damo-nlp-sg.github.io/DAMO-SeaLLMs/) (Large Language Models for Southeast Asian languages) family. It is the first large audio-language model (LALM) designed to support multiple Southeast Asian languages, including **Indonesian (id), Thai (th), and Vietnamese (vi), alongside English (en) and Chinese (zh)**.
 
233
  Corresponding Author: Wenxuan Zhang ([[email protected]](mailto:[email protected]))
234
  ```
235
  @misc{SeaLLMs-Audio,
236
+ title={SeaLLMs-Audio: Large Audio-Language Models for Southeast Asia},
237
+ author={Chaoqun Liu and Mahani Aljunied and Guizhen Chen and Hou Pong Chan and Weiwen Xu and Yu Rong and Wenxuan Zhang},
238
+ year={2025},
239
+ eprint={2511.01670},
240
+ archivePrefix={arXiv},
241
+ url={https://arxiv.org/abs/2511.01670},
242
  }
243
  ```
244